Assessment of Lettuce (Lactuta sativa) Crop Health Using Backpropagation Neural Network
Authors: Ira C. Valenzuela, Argel A. Bandala, and Elmer P. Dadios
Abstract
The determination of the healthiness of a crop is relevant in ensuring a high agricultural yield. The growth rate and the productivity are the factors that can help to establish the expected yield. This is done by computing the crop assessment index. The main objective of this study is to develop a simple color recognition algorithm using digital image processing techniques. This will eliminate subjectiveness in the classification of healthy and unhealthy lettuce. Moreover, this can help the farmers to assess the quality of the crops while growing them. The crop used in this study is romaine lettuce. The image processing was built using LabView Vision Assistant through RGB acquisition. The backpropagation of the artificial neural network was used to increase the efficiency of the system in assessing the quality of the lettuce. The total number of images used in the study is 280 wherein 15% were used for validation, 15% were used for testing, and 70% were used for training. The developed system proves to provide a better assessment of the lettuce crop health.